Clinical, brain, and multilevel clustering in early psychosis and affective stages

the PRONIA consortium

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Importance: Approaches are needed to stratify individuals in early psychosis stages beyond positive symptom severity to investigate specificity related to affective and normative variation and to validate solutions with premorbid, longitudinal, and genetic risk measures. 

Objective: To use machine learning techniques to cluster, compare, and combine subgroup solutions using clinical and brain structural imaging data from early psychosis and depression stages. 

Design, Setting, and Participants: A multisite, naturalistic, longitudinal cohort study (10 sites in 5 European countries; including major follow-up intervals at 9 and 18 months) with a referred patient sample of those with clinical high risk for psychosis (CHR-P), recent-onset psychosis (ROP), recent-onset depression (ROD), and healthy controls were recruited between February 1, 2014, to July 1, 2019. Data were analyzed between January 2020 and January 2022. 

Main Outcomes and Measures: A nonnegative matrix factorization technique separately decomposed clinical (287 variables) and parcellated brain structural volume (204 gray, white, and cerebrospinal fluid regions) data across CHR-P, ROP, ROD, and healthy controls study groups. Stability criteria determined cluster number using nested cross-validation. Validation targets were compared across subgroup solutions (premorbid, longitudinal, and schizophrenia polygenic risk scores). Multiclass supervised machine learning produced a transferable solution to the validation sample. 

Results: There were a total of 749 individuals in the discovery group and 610 individuals in the validation group. Individuals included those with CHR-P (n = 287), ROP (n = 323), ROD (n = 285), and healthy controls (n = 464), The mean (SD) age was 25.1 (5.9) years, and 702 (51.7%) were female. A clinical 4-dimensional solution separated individuals based on positive symptoms, negative symptoms, depression, and functioning, demonstrating associations with all validation targets. Brain clustering revealed a subgroup with distributed brain volume reductions associated with negative symptoms, reduced performance IQ, and increased schizophrenia polygenic risk scores. Multilevel results distinguished between normative and illness-related brain differences. Subgroup results were largely validated in the external sample. 

Conclusions and Relevance: The results of this longitudinal cohort study provide stratifications beyond the expression of positive symptoms that cut across illness stages and diagnoses. Clinical results suggest the importance of negative symptoms, depression, and functioning. Brain results suggest substantial overlap across illness stages and normative variation, which may highlight a vulnerability signature independent from specific presentations. Premorbid, longitudinal, and genetic risk validation suggested clinical importance of the subgroups to preventive treatments.

Original languageEnglish
Pages (from-to)677-689
Number of pages13
JournalJAMA psychiatry
Volume79
Issue number7
Early online date18 May 2022
DOIs
Publication statusPublished - Jul 2022

Bibliographical note

Funding Information:
Project funded by the European Union under the 7th Framework Programme under grant 602152. Dr Dwyer was supported by a NARSAD Young Investigator Grant (grant 30196). Dr Degenhardt was supported through grant COMMITMENT by the German Federal Ministry of Education and Research within the e:Med program and the EU COST program (COST Action EnGagE CA17130). Drs Popovic and Oeztuerk were supported by the Else-Kröner-Fresenius-Foundation through the Clinician Scientist Program EKFS-Translational Psychiatry. Dr Davatzikos reported funding from the National Institute of Mental Health project PHENOM (grant R01MH112070).

Funding Information:
supported by a NARSAD Young Investigator Grant (grant 30196). Dr Sanfelici reported personal fees from Lundbeck/Otsuka outside the submitted work. Dr Hauke reported grants from Swiss National Science Foundation (grant 200054) during the conduct of the study. Dr Schmidt-Kraepelin reported grants from the European Union during the conduct of the study and had a patent for DE 102020106962.6 issued. Ms Penzel reported grants from German Academic Exchange Service outside the submitted work. Dr Lichtenstein reported grants from Koeln Fortune Program/Faculty of Medicine, University of Cologne (grant 370/2020) during the conduct of the study. Dr Riecher-Rössler reports grants from the Zurich Program for Sustainable Development of Mental Health Services (ZInEP). Dr Andreou reports nonfinancial support from Sunovion and Lundbeck outside the submitted work. Dr Hietala reports personal fees from Orion, Otsuka, and Lundbeck and other support from Takeda during the conduct of the study. Dr Schirmer reported personal fees from GE Healthcare as an employee during the conduct of the study and outside the submitted work. Dr Michel reports grants from Swiss National Foundation during the conduct of the study. Dr Rössler reported grants from private foundation certified by health authorities during the conduct of the study. Dr Pantelis reported grants from Australian National Health & Medical Research Council during the conduct of the study, grants from Lundbeck Foundation outside the submitted work, and personal fees from Lundbeck Australia Pty Ltd outside the submitted work. Dr Lencer reported personal fees from Janssen and Otsuka outside the submitted work. Dr Borgwardt reported personal fees from Janssen outside the submitted work. Dr Noethen reports fees for memberships in advisory boards from the Lundbeck Foundation, the Robert-Bosch-Stiftung, HMG Systems Engineering GmbH, and the Medical-Scientific Editorial Office of the Deutsches Ärzteblatt; receives reimbursed travel expenses for a conference participation by Shire Deutschland GmbH; receives salary payments from Life & Brain GmbH, and holds shares in Life & Brain GmbH outside the submitted work. Dr Brambilla reported grants from University of Milan PRONIA project supported by a grant from the European Union under the 7th Framework Programme (grant 602152] during the conduct of the study. Dr Davatzikos reported funding from the National Institute of Mental Health project PHENOM (grant R01MH112070). Dr Upthegrove reported grants from European Union FP7 during the conduct of the study and reports personal fees from Sunovion and Vyvalife outside the submitted work. Dr Koutsouleris reported a patent for US10463313B2 issued. Drs Koutsouleris and Meisenzahl hold issued patent US20160192889A1 (adaptive pattern recognition for psychosis risk modelling’). Drs Koutsouleris, Ruhrmann, Riecher-Rössler, Romer, and Wood report grants from European Union during the conduct of the study. No other disclosures were reported.

Publisher Copyright:
© 2022 American Medical Association. All rights reserved.

Keywords

  • Adult
  • Brain/diagnostic imaging
  • Cluster Analysis
  • Female
  • Humans
  • Longitudinal Studies
  • Male
  • Psychotic Disorders/diagnostic imaging
  • Schizophrenia/diagnostic imaging

ASJC Scopus subject areas

  • Psychiatry and Mental health

Fingerprint

Dive into the research topics of 'Clinical, brain, and multilevel clustering in early psychosis and affective stages'. Together they form a unique fingerprint.

Cite this